BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230712T175159Z
LOCATION:3003\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20230710T133000
DTEND;TZID=America/Los_Angeles:20230710T170000
UID:dac_DAC 2023_sess172_TUT101@linklings.com
SUMMARY:A Journey to Optical Computing: From Physics Fundamentals to Hardw
 are-Software Co-Design, Automation, and Application
DESCRIPTION:Tutorial\n\nJiaqi Gu (University of Texas at Austin); Ulf Schl
 ichtmann (Technische Universität München); Cunxi Yu (University of Utah); 
 Chenghao Feng (University of Texas at Austin); Zhengqi Gao and Duane Bonin
 g (Massachusetts Institute of Technology); and Yingjie Li, Ruiyang Chen, M
 inhan Lou, and Berardi Sensale-Rodriguez (University of Utah)\n\nIn the po
 st-Moore era, conventional computing solutions of digital electronics have
  become a limiting factor in certain domains, most notably intelligent inf
 ormation processing. The proliferation of big data and artificial intellig
 ence (AI) has motivated the investigation of next-generation computing pla
 tforms to support low-latency, energy-efficient machine intelligence. With
  the advances in device, manufacturing, and integration technology, optics
 /photonics has attracted increasing attention in recent years and is consi
 dered to have great potential in key areas of communication, interconnects
 , sensing, and computing. Due to the ultra-fast speed and high parallelism
  of optics, computing platforms based on optical interconnects and process
 ing units can make transformative impacts in important use domains, e.g., 
 future datacenters, automotive, smart sensing, and intelligent edge. In re
 cent years, efforts have been made to facilitate the design automation sta
 ck of optical computing platforms and push forward the realization and pra
 ctical application of next-generation optical processors. However, as the 
 complexity of the heterogeneous mixed-signal computing platform escalates,
  significant design and optimization challenges need to be tackled. In ord
 er to have a scalable design closure and unleash the full power of optics,
  two critical threads need synergistic advancement along this journey, i.e
 ., cross-layer co-design and electronic-photonic design automation.\n\nIn 
 this tutorial, we will guide the interested audience on a journey toward n
 ext-generation optical processing platforms with a comprehensive introduct
 ion to the literature, co-design & automation technologies, hardware imple
 mentation, applications, as well as hands-on demos of optical AI computing
 .\nWe separate the tutorial into four talks covering integrated photonic c
 omputing, optical networks-on-chip and robustness analysis, synthesis for 
 field-programmable photonic arrays (FPPAs), and diffractive optical neural
  networks (DONNs). \n\nTalk I aims to introduce the literature and basics 
 of optical computing, as well as novel photonic integrated circuit (PIC) d
 esigns for both digital logic and analog AI computing. Talk I will also in
 troduce cross-layer co-design methodologies to enable area-efficient, nois
 e-robust, and self-learnable photonic AI engines, followed by a hands-on d
 emo to guide the audience to walk through the basic usage of our developed
  open-source optical AI library TorchONN. Talk II aims to introduce advanc
 ed topology and physical layout (place & route) optimization technologies 
 for scalable, efficient 2D/3D wavelength-routed optical networks-on-chip d
 esign. Talk II will also cover a thorough analysis and comprehensive solut
 ion to the process variation, noise robustness, and crosstalk issues of ph
 otonic integrated circuits. Talk III will introduce a novel field-programm
 able photonic array (FPPA) platform with its underlining physical theory a
 nd automatic synthesis techniques to realize various important functions, 
 such as routing, signal splitting, filtering, wavelength-division multiple
 xing, followed by a hands-on live demo (SPODE). Talk IV will introduce fre
 e-space diffractive optical neural networks (DONN) utilizing the natural p
 hysics of light diffraction and phase modulation of coherent light, with s
 uccessful applications demonstrated in image classification, segmentation,
  and graph learning. Talk IV will introduce the fundamentals of DONNs from
  Fourier optics, differentiable physics modeling, co-design algorithms, an
 d hardware realizations, following an end-to-end compilation framework (li
 ve demo) LightRidge.\n\nTopic: AI
END:VEVENT
END:VCALENDAR
